A method is disclosed for collecting and processing raw process data. The method includes processing the raw data through a process model to obtain a prediction of the process quality; processing this prediction through two dynamic transfer functions thus creating two intermediate signals; storing the two intermediate signals as a function of time; retrieving at the time of a real and validated measurement of the process quality from the history the absolute minimum value and maximum value of the two intermediate signals in the time period corresponding to a minimum and maximum specified deadtime, in which the absolute minimum value and maximum values define the minimum and maximum prediction possible; calculating the deviation as being the difference between the real and validated measurement and the uncertainty area encompassed between the minimum and maximum prediction possible; incorporating the deviation into the process model to calibrate the process model; and, repeating.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method for automatic on-line calibration of a process model for real-time prediction of process quality from raw process measurements which method comprises: a) collecting raw process data; b) processing data collected in step a) through the process model to obtain a prediction of the process quality; c) processing this prediction through two dynamic transfer functions thus creating two intermediate signals; d) storing the two intermediate signals obtained in step c) as a function of time; e) retrieving at the time of a real and validated measurement of the process quality from the history the absolute minimum value and maximum value of the two intermediate signals in the time period corresponding to a minimum and maximum specified deadtime, in which the absolute minimum value and maximum value define the minimum and maximum prediction possible; f) calculating the deviation as being the difference between the real and validated measurement and the uncertainty area encompassed between the minimum and maximum prediction possible as obtained in step e); g) proceeding with step i) if the absolute value of the deviation obtained in step f) is zero, or, proceeding with step h) if the absolute value of the deviation obtained in step f) is larger than zero; h) incorporating the deviation into the process model to calibrate the process model; and, i) starting over at step a).
2. The method of claim 1 , in which a Multiple Linear Regression process model is used.
3. The method of claim 1 , in which a Linear Dynamic process model is used.
4. The method of claim 1 , in which a Radial Basis Function Neural Network process model is used.
5. The method of claim 1 , in which in step h) a Kalman filter method is used to incorporate the deviation into the process model by adjusting the process model's linear parameters thereby upgrading the prediction and improving the process model by self learning.
6. The method of claim 5 , in which the Kalman filter is used in step h) under non steady-state conditions of the process.
7. The method of claim 1 , wherein the prediction in step (c) is processed through two independent dynamic transfer functions.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 17, 2001
April 15, 2008
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.